© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15038
    Prev
    Next
    INDEX
    Explanations

    http links and license information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĹãģı
    -0.23
    .za
    -0.17
    ings
    -0.15
    tures
    -0.15
    ¥
    -0.15
    lessness
    -0.15
    tres
    -0.15
    teen
    -0.15
    ndx
    -0.15
    teil
    -0.15
    POSITIVE LOGITS
    ities
    0.18
    даÑĢ
    0.17
    repid
    0.15
    ance
    0.15
    cliffe
    0.15
    apolis
    0.14
    /he
    0.14
    elly
    0.14
    æĻ°
    0.14
    .swagger
    0.14
    Activations Density 0.442%

    No Known Activations